@inproceedings{gao-etal-2023-data,
title = "Data Augmentation with Diversified Rephrasing for Low-Resource Neural Machine Translation",
author = "Gao, Yuan and
Hou, Feng and
Jahnke, Huia and
Wang, Ruili",
editor = "Utiyama, Masao and
Wang, Rui",
booktitle = "Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track",
month = sep,
year = "2023",
address = "Macau SAR, China",
publisher = "Asia-Pacific Association for Machine Translation",
url = "https://aclanthology.org/2023.mtsummit-research.4",
pages = "35--47",
abstract = "Data augmentation is an effective way to enhance the performance of neural machine translation models, especially for low-resource languages. Existing data augmentation methods are either at a token level or a sentence level. The data augmented using token level methods lack syntactic diversity and may alter original meanings. Sentence level methods usually generate low-quality source sentences that are not semantically paired with the original target sentences. In this paper, we propose a novel data augmentation method to generate diverse, high-quality and meaning-preserved new instances. Our method leverages high-quality translation models trained with high-resource languages to rephrase an original sentence by translating it into an intermediate language and then back to the original language. Through this process, the high-performing translation models guarantee the quality of the rephrased sentences, and the syntactic knowledge from the intermediate language can bring syntactic diversity to the rephrased sentences. Experimental results show our method can enhance the performance in various low-resource machine translation tasks. Moreover, by combining our method with other techniques that facilitate NMT, we can yield even better results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2023-data">
<titleInfo>
<title>Data Augmentation with Diversified Rephrasing for Low-Resource Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huia</namePart>
<namePart type="family">Jahnke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruili</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asia-Pacific Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Macau SAR, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data augmentation is an effective way to enhance the performance of neural machine translation models, especially for low-resource languages. Existing data augmentation methods are either at a token level or a sentence level. The data augmented using token level methods lack syntactic diversity and may alter original meanings. Sentence level methods usually generate low-quality source sentences that are not semantically paired with the original target sentences. In this paper, we propose a novel data augmentation method to generate diverse, high-quality and meaning-preserved new instances. Our method leverages high-quality translation models trained with high-resource languages to rephrase an original sentence by translating it into an intermediate language and then back to the original language. Through this process, the high-performing translation models guarantee the quality of the rephrased sentences, and the syntactic knowledge from the intermediate language can bring syntactic diversity to the rephrased sentences. Experimental results show our method can enhance the performance in various low-resource machine translation tasks. Moreover, by combining our method with other techniques that facilitate NMT, we can yield even better results.</abstract>
<identifier type="citekey">gao-etal-2023-data</identifier>
<location>
<url>https://aclanthology.org/2023.mtsummit-research.4</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>35</start>
<end>47</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Augmentation with Diversified Rephrasing for Low-Resource Neural Machine Translation
%A Gao, Yuan
%A Hou, Feng
%A Jahnke, Huia
%A Wang, Ruili
%Y Utiyama, Masao
%Y Wang, Rui
%S Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track
%D 2023
%8 September
%I Asia-Pacific Association for Machine Translation
%C Macau SAR, China
%F gao-etal-2023-data
%X Data augmentation is an effective way to enhance the performance of neural machine translation models, especially for low-resource languages. Existing data augmentation methods are either at a token level or a sentence level. The data augmented using token level methods lack syntactic diversity and may alter original meanings. Sentence level methods usually generate low-quality source sentences that are not semantically paired with the original target sentences. In this paper, we propose a novel data augmentation method to generate diverse, high-quality and meaning-preserved new instances. Our method leverages high-quality translation models trained with high-resource languages to rephrase an original sentence by translating it into an intermediate language and then back to the original language. Through this process, the high-performing translation models guarantee the quality of the rephrased sentences, and the syntactic knowledge from the intermediate language can bring syntactic diversity to the rephrased sentences. Experimental results show our method can enhance the performance in various low-resource machine translation tasks. Moreover, by combining our method with other techniques that facilitate NMT, we can yield even better results.
%U https://aclanthology.org/2023.mtsummit-research.4
%P 35-47
Markdown (Informal)
[Data Augmentation with Diversified Rephrasing for Low-Resource Neural Machine Translation](https://aclanthology.org/2023.mtsummit-research.4) (Gao et al., MTSummit 2023)
ACL